© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13194
    Prev
    Next
    INDEX
    Explanations

    words that end in a 't' sound or short snippets of foreign languages

    oai_token-act-pair · gemini-2.0-flash

    Code snippets and fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yourself
    -0.74
     you
    -0.65
    yourself
    -0.57
     nakalista
    -0.56
     your
    -0.54
    зья
    -0.53
     nonUne
    -0.51
     Anda
    -0.51
     YOURSELF
    -0.50
     vous
    -0.49
    POSITIVE LOGITS
    lapi
    0.58
    ItemBackground
    0.57
     OFDb
    0.52
    UnknownFields
    0.52
     AssemblyCulture
    0.52
    seamnă
    0.51
     Domes
    0.51
    They
    0.49
     Réponses
    0.49
    脚注の使い方
    0.48
    Activations Density 0.945%

    No Known Activations